Maternal and child healthcare stands as a cornerstone of public health, with the well-being of mothers and infants directly influencing the vitality of communities. Despite advances in medical science, challenges persist in predicting pregnancy outcomes, reducing infant mortality rates, and addressing maternal health risks effectively. Research has been made to predict infant mortality in many developed and developing countries. However, much more work still needs to be done in the Indian context. Hence, in this paper, we attempt to understand the infant mortality problem in India through machine learning. More specifically, we find factors correlated with infant mortality and assess whether (and to what extent) infant mortality can be predicted using classical machine learning algorithms. The classification performance of conventional machine learning algorithms was not satisfactory. The decision tree classifier was the best for correctly predicting the death of a child within one year of birth with precision of 30% and recall of 25%. This implies that more advanced techniques for predicting death must be investigated.